Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    with

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     beb
    -0.07
    еними
    -0.07
     args
    -0.06
    -*
    -0.06
     وصلات
    -0.06
     festive
    -0.06
    _slope
    -0.06
    よび
    -0.06
    正常
    -0.06
    wend
    -0.06
    POSITIVE LOGITS
     CMP
    0.07
    [date
    0.07
     AHL
    0.06
     fullPath
    0.06
     ",↵
    0.06
    -wife
    0.06
     behaved
    0.06
    ایت
    0.06
    =yes
    0.06
    備
    0.06
    Act Density 0.000%

    No Known Activations